Classification of multisensor remote-sensing images by structured neural networks

Abstract- This paper proposes the application of structured neural networks to classification of multisensor remote-sensing images. The purpose of our approach is to allow the interpretation of the “network behavior, ” as it can be utilized by photointer-preters for the validation of the neural classifier. In addition, our approach gives a criterion for defining the network architecture, so avoiding the classical trial-and-error process. First of all, the architecture of structured multilayer feedforward networks is tai-lored to a multisensor classification problem. Then, such networks are trained to solve the problem by the error backpropagation algorithm. Finally, they are transformed into equivalent networks to obtain a simplified representation. The resulting equivalent networks may be interpreted as a hierarchical arrangement of “committees ” that accomplish the classification task by checking on a set of explicit constraints on input data. Experimental results on a multisensor (optical and SAR) data set are described in terms of both classification accuracy and network interpretation. Comparisons with fully connected neural networks and with the k-nearest neighbor classifier are also made. I